EP4298605A4 - ONLINE TRAINING-BASED ENCODER TUNING WITH MULTI-MODEL SELECTION IN NEURAL IMAGE COMPRESSION - Google Patents
ONLINE TRAINING-BASED ENCODER TUNING WITH MULTI-MODEL SELECTION IN NEURAL IMAGE COMPRESSION Download PDFInfo
- Publication number
- EP4298605A4 EP4298605A4 EP23773160.9A EP23773160A EP4298605A4 EP 4298605 A4 EP4298605 A4 EP 4298605A4 EP 23773160 A EP23773160 A EP 23773160A EP 4298605 A4 EP4298605 A4 EP 4298605A4
- Authority
- EP
- European Patent Office
- Prior art keywords
- image compression
- model selection
- online training
- based encoder
- neural image
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T9/00—Image coding
- G06T9/002—Image coding using neural networks
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N19/00—Methods or arrangements for coding, decoding, compressing or decompressing digital video signals
- H04N19/10—Methods or arrangements for coding, decoding, compressing or decompressing digital video signals using adaptive coding
- H04N19/102—Methods or arrangements for coding, decoding, compressing or decompressing digital video signals using adaptive coding characterised by the element, parameter or selection affected or controlled by the adaptive coding
- H04N19/103—Selection of coding mode or of prediction mode
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N19/00—Methods or arrangements for coding, decoding, compressing or decompressing digital video signals
- H04N19/10—Methods or arrangements for coding, decoding, compressing or decompressing digital video signals using adaptive coding
- H04N19/134—Methods or arrangements for coding, decoding, compressing or decompressing digital video signals using adaptive coding characterised by the element, parameter or criterion affecting or controlling the adaptive coding
- H04N19/146—Data rate or code amount at the encoder output
- H04N19/149—Data rate or code amount at the encoder output by estimating the code amount by means of a model, e.g. mathematical model or statistical model
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N19/00—Methods or arrangements for coding, decoding, compressing or decompressing digital video signals
- H04N19/10—Methods or arrangements for coding, decoding, compressing or decompressing digital video signals using adaptive coding
- H04N19/169—Methods or arrangements for coding, decoding, compressing or decompressing digital video signals using adaptive coding characterised by the coding unit, i.e. the structural portion or semantic portion of the video signal being the object or the subject of the adaptive coding
- H04N19/17—Methods or arrangements for coding, decoding, compressing or decompressing digital video signals using adaptive coding characterised by the coding unit, i.e. the structural portion or semantic portion of the video signal being the object or the subject of the adaptive coding the unit being an image region, e.g. an object
- H04N19/172—Methods or arrangements for coding, decoding, compressing or decompressing digital video signals using adaptive coding characterised by the coding unit, i.e. the structural portion or semantic portion of the video signal being the object or the subject of the adaptive coding the unit being an image region, e.g. an object the region being a picture, frame or field
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N19/00—Methods or arrangements for coding, decoding, compressing or decompressing digital video signals
- H04N19/46—Embedding additional information in the video signal during the compression process
Landscapes
- Engineering & Computer Science (AREA)
- Multimedia (AREA)
- Signal Processing (AREA)
- General Physics & Mathematics (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Evolutionary Computation (AREA)
- Artificial Intelligence (AREA)
- Algebra (AREA)
- Mathematical Analysis (AREA)
- Mathematical Optimization (AREA)
- Pure & Applied Mathematics (AREA)
- Compression Of Band Width Or Redundancy In Fax (AREA)
- Image Analysis (AREA)
- Compression Or Coding Systems Of Tv Signals (AREA)
Applications Claiming Priority (3)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| US202263325115P | 2022-03-29 | 2022-03-29 | |
| US18/122,651 US20230316588A1 (en) | 2022-03-29 | 2023-03-16 | Online training-based encoder tuning with multi model selection in neural image compression |
| PCT/US2023/016042 WO2023192096A1 (en) | 2022-03-29 | 2023-03-23 | Online training-based encoder tuning with multi model selection in neural image compression |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| EP4298605A1 EP4298605A1 (en) | 2024-01-03 |
| EP4298605A4 true EP4298605A4 (en) | 2024-07-17 |
Family
ID=88193200
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| EP23773160.9A Pending EP4298605A4 (en) | 2022-03-29 | 2023-03-23 | ONLINE TRAINING-BASED ENCODER TUNING WITH MULTI-MODEL SELECTION IN NEURAL IMAGE COMPRESSION |
Country Status (4)
| Country | Link |
|---|---|
| US (1) | US20230316588A1 (en) |
| EP (1) | EP4298605A4 (en) |
| CN (1) | CN117461055A (en) |
| WO (1) | WO2023192096A1 (en) |
Families Citing this family (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2025160707A1 (en) * | 2024-01-29 | 2025-08-07 | Intel Corporation | Intelligent ai generated video guided by hardware encoder |
| CN119342214B (en) * | 2024-12-20 | 2025-03-11 | 国网安徽省电力有限公司电力科学研究院 | Image coding and decoding model training method and system based on deviation control |
Family Cites Families (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2020008104A1 (en) * | 2018-07-02 | 2020-01-09 | Nokia Technologies Oy | A method, an apparatus and a computer program product for image compression |
| US11842531B2 (en) * | 2020-02-28 | 2023-12-12 | United States Postal Service | System and method for image compression |
| US12058348B2 (en) * | 2020-04-17 | 2024-08-06 | Qualcomm Incorporated | Parallelized rate-distortion optimized quantization using deep learning |
| EP4144087A1 (en) * | 2020-04-29 | 2023-03-08 | Deep Render Ltd | Image compression and decoding, video compression and decoding: methods and systems |
-
2023
- 2023-03-16 US US18/122,651 patent/US20230316588A1/en active Pending
- 2023-03-23 EP EP23773160.9A patent/EP4298605A4/en active Pending
- 2023-03-23 CN CN202380010803.2A patent/CN117461055A/en active Pending
- 2023-03-23 WO PCT/US2023/016042 patent/WO2023192096A1/en not_active Ceased
Non-Patent Citations (5)
| Title |
|---|
| GUO LU ET AL: "Content Adaptive and Error Propagation Aware Deep Video Compression", ARXIV.ORG, CORNELL UNIVERSITY LIBRARY, 201 OLIN LIBRARY CORNELL UNIVERSITY ITHACA, NY 14853, 25 March 2020 (2020-03-25), XP081629309 * |
| JIAHENG LIU ET AL: "A Unified End-to-End Framework for Efficient Deep Image Compression", ARXIV.ORG, CORNELL UNIVERSITY LIBRARY, 201 OLIN LIBRARY CORNELL UNIVERSITY ITHACA, NY 14853, 24 May 2020 (2020-05-24), XP081660636 * |
| NANNAN ZOU ET AL: "Learning to Learn to Compress", ARXIV.ORG, CORNELL UNIVERSITY LIBRARY, 201 OLIN LIBRARY CORNELL UNIVERSITY ITHACA, NY 14853, 1 May 2021 (2021-05-01), XP081950101 * |
| See also references of WO2023192096A1 * |
| WANG YEFEI ET AL: "Ensemble Learning-Based Rate-Distortion Optimization for End-to-End Image Compression", IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY, IEEE, USA, vol. 31, no. 3, 5 June 2020 (2020-06-05), pages 1193 - 1207, XP011843402, ISSN: 1051-8215, [retrieved on 20210304], DOI: 10.1109/TCSVT.2020.3000331 * |
Also Published As
| Publication number | Publication date |
|---|---|
| WO2023192096A1 (en) | 2023-10-05 |
| CN117461055A (en) | 2024-01-26 |
| US20230316588A1 (en) | 2023-10-05 |
| EP4298605A1 (en) | 2024-01-03 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| EP4298605A4 (en) | ONLINE TRAINING-BASED ENCODER TUNING WITH MULTI-MODEL SELECTION IN NEURAL IMAGE COMPRESSION | |
| EP4500472A4 (en) | ONLINE TRAINING-BASED ENCODER TUNING IN NEURAL IMAGE COMPRESSION | |
| EP3815370A4 (en) | INTRA PREDICTION USING A CROSS-COMPONENT LINEAR MODEL IN VIDEO CODING | |
| DK3831064T3 (en) | REFERENCE IMAGE CONTROL IN VIDEO CODING | |
| IL287017A (en) | Affine linear weighted intra prediction in video coding | |
| EP3939314A4 (en) | TRANSFORMATION CODING BASED ON MATRIX-BASED INTRA PREDICTION | |
| DK3906665T3 (en) | SUBIMAGE DIMENSIONING IN VIDEO CODING | |
| IL280228A (en) | Video encoder, video encoder and corresponding encoding and decoding methods | |
| EP3833021A4 (en) | IMAGE ENCODING / DECODING METHOD AND DEVICE USING INTRAPREDICTION | |
| SG11202108267QA (en) | Subblock coding by generalized intra prediction in video coding | |
| IL261245A (en) | Structure learning in convolutional neural systems | |
| EP3928511A4 (en) | STEP-BY-STEP DECODE REFRESH IN VIDEO ENCODING | |
| EP4150535A4 (en) | IMPROVED KNOWLEDGE DISTILLATION BY USING BACKWARD PASS KNOWLEDGE IN NEURONAL NETWORKS | |
| BR112016028547A2 (en) | adaptive block color-space conversion coding | |
| EP4373094C0 (en) | Image coding and decoding devices using a transform-based method | |
| EP4331232A4 (en) | CONTENT-ADAPTIVE ONLINE TRAINING WITH FEATURE REPLACEMENT IN NEURAL IMAGE COMPRESSION | |
| EP4168985A4 (en) | MULTI-LEVEL IMAGE COMPRESSION | |
| DK3967038T3 (en) | REFERENCE IMAGE HANDLING IN LAYERED VIDEO CODING | |
| EP4409911A4 (en) | VIDEO CODING WITH SELECABLE NEURAL NETWORK-BASED CODING TOOLS | |
| EP4205069A4 (en) | PIPELINES FOR PROCESSING CAMERA IMAGES OR VIDEOS WITH NEURAL EMBEDDMENT | |
| EP3942495C0 (en) | DEVICE FOR TRANSCRIPTING APPEARANCES IN AN IMAGE IN TEXT USING MACHINE LEARNING | |
| EP4276770C0 (en) | OBJECT RE-IDENTIFICATION IN VIDEO DATA STREAMS | |
| EP4413410A4 (en) | IMAGE WITH ENHANCED RESOLUTION | |
| EP4370679A4 (en) | MOTOR NEURON EXPRESSION ENHANCERS | |
| EP4136853A4 (en) | BLOCKWISE ENTROPIE CODING PROCEDURE IN COMPRESSION OF NEURAL IMAGES |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| STAA | Information on the status of an ep patent application or granted ep patent |
Free format text: STATUS: UNKNOWN |
|
| STAA | Information on the status of an ep patent application or granted ep patent |
Free format text: STATUS: THE INTERNATIONAL PUBLICATION HAS BEEN MADE |
|
| PUAI | Public reference made under article 153(3) epc to a published international application that has entered the european phase |
Free format text: ORIGINAL CODE: 0009012 |
|
| STAA | Information on the status of an ep patent application or granted ep patent |
Free format text: STATUS: REQUEST FOR EXAMINATION WAS MADE |
|
| 17P | Request for examination filed |
Effective date: 20230929 |
|
| AK | Designated contracting states |
Kind code of ref document: A1 Designated state(s): AL AT BE BG CH CY CZ DE DK EE ES FI FR GB GR HR HU IE IS IT LI LT LU LV MC ME MK MT NL NO PL PT RO RS SE SI SK SM TR |
|
| REG | Reference to a national code |
Ref country code: DE Ref legal event code: R079 Free format text: PREVIOUS MAIN CLASS: G06T0009000000 Ipc: H04N0019103000 |
|
| A4 | Supplementary search report drawn up and despatched |
Effective date: 20240619 |
|
| RIC1 | Information provided on ipc code assigned before grant |
Ipc: G06T 9/00 20060101ALI20240613BHEP Ipc: H04N 19/46 20140101ALI20240613BHEP Ipc: H04N 19/172 20140101ALI20240613BHEP Ipc: H04N 19/149 20140101ALI20240613BHEP Ipc: H04N 19/103 20140101AFI20240613BHEP |
|
| DAV | Request for validation of the european patent (deleted) | ||
| DAX | Request for extension of the european patent (deleted) |